# BRAINIAC Service Account Anomaly Detector

> BRAINIAC Service Account Anomaly Detector is a paid API for AI agents from www.brainiac.software, paid per call via x402, $0.04/call, status unknown (last checked 2026-11-12).

Analyzes service account authentication events to detect behavioral anomalies such as off-hours activity, interactive logins, and suspicious IP patterns that may indicate credential theft or misuse.

## Facts

- Endpoint: POST https://www.brainiac.software/api/v1/identity-security/service-account-anomaly-detect?utm_source=zero.xyz
- Price: $0.04/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/brainiac-service-account-anomaly-detector-426545f1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_nbEfFsWx3MXsiEwWIXGue

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability brainiac-service-account-anomaly-detector-426545f1 -d '<json body>'
```

Example prompt: Can you analyze these service account authentication logs and tell me if there's anything suspicious — I'm seeing activity from multiple IPs and some late-night logins for our svc_backup account that might indicate credential theft?

## When to prefer this

Use this endpoint when you need behavioral anomaly detection specifically for non-human service accounts, rather than general user authentication analysis. It is particularly suited for detecting credential theft or misuse via patterns like off-hours activity, interactive logins, multi-application access, and multiple source IPs — signals that are especially meaningful for accounts that should only be used by automated systems. Prefer it over generic SIEM queries when you need a structured, pay-per-call analysis without standing up dedicated security infrastructure.

## Known failure modes

- Empty or malformed event array returns no findings
- Events missing required fields like timestamps or outcomes may be skipped
- Very low event counts may not trigger behavioral thresholds
- Truncated CSV or JSON input exceeding 200,000 character limit rejected
- Base64-encoded file exceeding 12MB limit rejected
- Missing asOf timestamp may affect time-based anomaly rules
- Ambiguous eventType values may not trigger role-based heuristics

## How this service works

Pay-per-call APIs for AI agents: OFAC sanctions screening, compliance checks, token security, and Base chain data via x402. No account. Fixed USDC price. MCP-ready.

## Output

Returns a JSON object with a list of anomaly items, each containing: a unique ID, title, first/last seen timestamps, source description, status (signal/finding), reasons for flagging (e.g. off_hours_activity, interactive_service_login, many_source_ips), evidence array with timestamped facts and confidence levels, observed facts summary, inferred threat description, related event IDs, mitigating factors, and a confirmed compromise boolean. Also includes a top-level status field and a findings array with structured finding codes.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "csv": {
   "type": "string",
   "maxLength": 200000
  },
  "asOf": {
   "type": "string",
   "maxLength": 40
  },
  "file": {
   "type": "object",
   "required": [
    "fileBase64"
   ],
   "properties": {
    "role": {
     "type": "string",
     "maxLength": 80
    },
    "filename": {
     "type": "string",
     "maxLength": 180,
     "minLength": 1
    },
    "mediaType": {
     "enum": [
      "text/plain",
      "text/csv",
      "application/json",
      "application/octet-stream"
     ],
     "type": "string"
    },
    "fileBase64": {
     "type": "string",
     "maxLength": 12000000,
     "minLength": 1
    }
   },
   "additionalProperties": false
  },
  "json": {
   "type": "string",
   "maxLength": 200000
  },
  "text": {
   "type": "string",
   "maxLength": 200000
  },
  "files": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "fileBase64"
    ],
    "properties": {
     "role": {
      "type": "string",
      "maxLength": 80
     },
     "filename": {
      "type": "string",
      "maxLength": 180,
      "minLength": 1
     },
     "mediaType": {
      "enum": [
       "text/plain",
       "text/csv",
       "application/json",
       "application/octet-stream"
      ],
      "type": "string"
     },
     "fileBase64": {
      "type": "string",
      "maxLength": 12000000,
      "minLength": 1
     }
    },
    "additionalProperties": false
   },
   "maxItems": 20
  },
  "events": {
   "type": "array",
   "items": {
    "type": "object",
    "properties": {
     "at": {
      "type": "string",
      "maxLength": 40
     },
     "id": {
      "type": "string",
      "maxLength": 80
     },
     "ip": {
      "type": "string",
      "maxLength": 80
     },
     "asn": {
      "type": "string",
      "maxLength": 80
     },
     "isVpn": {
      "type": "boolean"
     },
     "action": {
      "type": "string",
      "maxLength": 120
     },
     "labels": {
      "type": "array",
      "items": {
       "type": "string",
       "maxLength": 80
      },
      "maxItems": 40
     },
     "source": {
      "type": "string",
      "maxLength": 200
     },
     "userId": {
      "type": "string",
      "maxLength": 120
     },
     "geoCity": {
      "type": "string",
      "maxLength": 120
     },
     "isProxy": {
      "type": "boolean"
     },
     "outcome": {
      "enum": [
       "success",
       "failure",
       "challenge",
       "unknown"
      ],
      "type": "
… (truncated)
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "items": [
   {
    "id": "service-anomaly-svc_backup",
    "title": "Unusual service account activity",
    "lastAt": "2026-11-04T04:00:00.000Z",
    "source": "Caller-supplied service-account events; local behavioural rules",
    "status": "signal",
    "firstAt": "2026-11-04T02:10:00.000Z",
    "reasons": [
     "off_hours_activity",
     "interactive_service_login",
     "many_applications",
     "many_source_ips",
     "human_client_fingerprint"
    ],
    "detector": "service-account-anomaly-detect",
    "evidence": [
     {
      "at": "2026-11-04T02:10:00.000Z",
      "fact": "interactive_login outcome=success; app=console; ip=203.0.113.10",
      "eventId": "E1",
      "inference": "Service-account anomaly is behavioural only; not confirmed compromise.",
      "confidence": "medium"
     },
     {
      "at": "2026-11-04T03:00:00.000Z",
      "fact": "authentication outcome=success; app=s3; ip=198.51.100.20",
      "eventId": "E2",
      "inference": "Service-account anomaly is behavioural only; not confirmed compromise.",
      "confidence": "medium"
     },
     {
      "at": "2026-11-04T03:30:00.000Z",
      "fact": "authentication outcome=failure; app=github; ip=192.0.2.30",
      "eventId": "E3",
      "inference": "Service-account anomaly is behavioural only; not confirmed compromise.",
      "confidence": "medium"
     },
     {
      "at": "2026-11-04T04:00:00.000Z",
      "fact": "authentication outcome=success; app=vpn; ip=203.0.113.40",
      "eventId": "E4",
      "inference": "Service-account anomaly is behavioural only; not confirmed compromise.",
      "confidence": "medium"
     }
    ],
    "confidence": "high",
    "observedFacts": [
     "4 events outside 05:00–22:00 UTC.",
     "1 interactive-style login(s) for a service account.",
     "Service account touched 4 applications/resources.",
     "4 source IPs for service account activity."
    ],
    "inferredThreat": "Service accounts used interactively or across many apps/IPs can indicate misuse or credential theft.",
    "relatedEventIds": [
     "E1",
     "E2",
     "E3",
     "E4"
    ],
    "mitigatingFactors": [],
    "confirmedCompromise": false
   }
  ],
  "status": "detected",
  "findings": [
   {
    "code": "service_account_anomaly",
    "kind": "conflict",
    "detail": "Service-account anomalies: off_hours_activity, interactive_service_login, many_applications, many_source_ips, human_client_fingerprint (confirmedCompromise=false).
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/brainiac-service-account-anomaly-detector-426545f1/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from www.brainiac.software](https://www.zero.xyz/host/www.brainiac.software/llms.txt)
